SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2081–2090 of 15113 papers

TitleStatusHype
Feasibility Consistent Representation Learning for Safe Reinforcement LearningCode1
Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning—0
Highway Graph to Accelerate Reinforcement LearningCode0
Comparisons Are All You Need for Optimizing Smooth Functions—0
Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning—0
Large Language Models are Biased Reinforcement LearnersCode0
Optimal control barrier functions for RL based safe powertrain control—0
Combined film and pulse heating of lithium ion batteries to improve performance in low ambient temperature—0
Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses—0
LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions—0
Show:102550
← PrevPage 209 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified